PhD Position in Deep Learning for Predicting Poverty from Satellite Images Chalmers University of Technology

-






PhD Position in Deep Learning for Predicting Poverty from Satellite Images Chalmers University of Technology


The data science and AI division at CSE is recruiting a PhD student for a project in Deep Learning for Predicting Poverty from Satellite Images.

The position is advertised within the research project Poverty traps in Africa, funded by FORMAS. FORMAS is a government research council for sustainable development. Its areas of activity include the environment, agricultural sciences, and spatial planning.

About 900 million people—one-third in Africa—live in extreme poverty. Operating on the assumption that life in impoverished communities is fundamentally so different that it can trap people in cycles of deprivation ('poverty traps'), major development agencies have deployed a stream of development projects to break these cycles ('poverty targeting'). However, scholars are currently unable to answer questions such as in what capacity do poverty traps exist; to what extent do these interventions release communities from such traps—as they are held back by a data challenges. There is a lack of geo-temporal poverty data; this project will develop new methods to produce such data. Consequently, the aim of this project is to identify to what extent African communities are trapped in poverty and explain how competing development interventions alter these communities' prospects to free themselves from deprivation. To achieve this aim, the project will (i) develop machine learning algorithms to identify poverty traps from satellite images (e.g. NASA's Landsat mission) between 1980s to 2020; (ii) use these remote sensing derived poverty data to examine how World Bank versus Chinese development programs target and communities; (iii) investigate the extent to which such analysis can be used to draw causal conclusions about the impact of development pograms (iv) using this foundational work, scale up the results from (i) – (iii) to validate them and develop a theory of the varieties of poverty traps and targeting. Lastly, (iv) To produce a statistical package—PovertyMachine—that enables us, and other scholars, to produce poverty estimates from new images (i).

The doctoral student is expected to produce a Ph.D. thesis contributing to primarly satisfying the project's first and third aims: "To develop machine learning and causal inference algorithms to identify poverty levels and poverty traps using satellite images, of African communities over time and space, on a quarterly basis, from the 1980s to 2020."

And secondarily contribututing to satisfying the project's fourth aim: "To produce a statistical package—PovertyMachine—that enables us, and other scholars, to produce poverty estimates from new images (i)."

The project is a collaboration between Chalmers University of Technology and the Department of Sociology, University of Gothenburg. Accordingly, although the student will pursue a PhD in machine learning within computer science and engineering at Chalmers, this person expected to have an interest in social-scientific issues and interdisciplinary research. 

Major responsibilities
Your major responsibilities as a PhD student is to pursue your doctoral studies within the framework of the outlined research project. You will be enrolled in a graduate program in the Department of Computer Science and Engineering. You are expected to develop your own ideas and communicate scientific results orally as well as in written form. In addition, the position will include 20% departmental work, mostly teaching duties in Chalmers' undergraduate and masters-level courses or performing other duties corresponding to 20% of working hours.

Position summary
Full-time temporary employment. The position is limited to a maximum of five years.

Qualifications
To qualify as a PhD student, you must have a master's-level degree, or a four-year bachelor's degree, corresponding to at least 240 higher education credits in a relevant field. The position requires sound verbal and written communication skills in Swedish and English. If Swedish is not your native language, you should be able to teach in Swedish after two years. Chalmers offers Swedish courses.

Chalmers continuously strives to be an attractive employer. Equality and diversity are substantial foundations in all activities at Chalmers.

Our offer to you
Chalmers offers a cultivating and inspiring working environment in the dynamic city of Gothenburg. 
Read more about working at Chalmers and our benefits for employees.

Application procedure
The application should be marked with Ref 20200430 and written in English. The application should be sent electronically and be attached as pdf-files, as below:

CV: (Please name the document: CV, Family name, Ref. number)
• CV
• Other, for example previous employments or leadership qualifications and positions of trust.
• Two references that we can contact.

Personal letter: (Please name the document as: Personal letter, Family name, Ref. number)
1-3 pages where you:
• Introduce yourself
• Describe your previous experience of relevance for the position (e.g. education, thesis work and, if applicable, any other research activities)
• Describe your future goals and future research focus

Other documents:
• Copies of bachelor and/or master's thesis.
• Attested copies and transcripts of completed education, grades and other certificates, e.g. TOEFL test results.

Please use the button at the foot of the page to reach the application form. The files may be compressed (zipped).

Application deadline: 21 October, 2020

For questions, please contact:
Fredrik Johansson, CSE DSAI, fredrik.johansson@chalmers.se






Vineesh V
Assistant Professor of Geography,
Directorate of Education,
Government of Kerala.
https://www.facebook.com/Applied.Geography
http://geogisgeo.blogspot.com

Comments

Post a Comment

Popular posts from this blog

Spatial feature manipulation in remote sensing

-
Image
Spatial feature manipulation in remote sensing refers to the process of altering or modifying the spatial characteristics of a particular feature in an image or data set. This can be done for a variety of reasons, such as to improve the accuracy or clarity of the image, to enhance the interpretability of the data, or to extract specific information from the image. One common method of spatial feature manipulation is resampling, which involves changing the resolution or spatial extent of an image. This can be done to match the resolution of other data sets, to reduce the size of the image for faster processing, or to increase the resolution for greater detail. Another technique is spatial filtering, which involves applying mathematical operations to the image data to remove noise or highlight specific features. This can be done using convolution filters, which apply a pre-defined mathematical function to the image data, or using image enhancement techniques, such as contrast stretching
Read more

Denman Glacier Losing Some of Its Footing

-
Image
Denman Glacier Losing Some of Its Footing Using a combination of satellite sensors, scientists recently found that Denman Glacier has been retreating both above and below the water line. That one glacier in East Antarctica holds as much ice as half of West Antarctica, so scientists are concerned about its stability. From 1996 to 2018, the grounding line along the western flank of Denman Glacier retreated 5.4 kilometers (3.4 miles), according to a new study by scientists from NASA's Jet Propulsion Laboratory and the University of California, Irvine (UCI). The grounding line is the point at which a glacier last touches the seafloor before it begins to float. Behind the grounding line, the ice is attached to the bedrock; beyond it, glacial ice floats on the ocean as an ice tongue or shelf. The retreat of the grounding line at Denman means more of the glacier's underside is now in contact with water that could warm and melt it from below. If the grounding line continues to retreat,
Read more

Difference between Kriging and IDW

-
Image
Difference between Kriging and IDW. What does kriging mean? least squares estimate. Kriging is a type of regression that gives a least squares estimate of data (Remy et. ... Unlike linear regression or inverse distance weighted interpolation, kriging interpolation is based primarily on empirical observations, the observed sample data points, rather than on a pre-assumed model. What is GIS IDW? Inverse Distance Weighted (IDW) is a method of interpolation that estimates cell values by averaging the values of sample data points in the neighborhood of each processing cell. ... Specifying a lower power will give more influence to the points that are farther away, resulting in a smoother surface. Which interpolation method is best? The most used and promising techniques are universal Kriging and linear regression models in combination with Kriging (residual Kriging) or IDW. E.g.: Air temperature data – Kriging is most likely to produce the best estimation of a continuous surface, followed by
Read more